© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2356
    Prev
    Next
    INDEX
    Explanations

    terms related to manufacturing and scientific testing processes

    oai_token-act-pair · gemini-2.0-flash

    scientific/chemical processes

    np_max-act · gemini-2.0-flash

    say "leading space" Method used: 2 — because all following tokens start with a leading space — say "leading space"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hochspringen
    -0.75
     continuant
    -0.61
     continúas
    -0.60
    
    -0.60
    참고
    -0.59
    öglichkeiten
    -0.59
    AlterField
    -0.58
     Мексичка
    -0.57
    ;;)
    -0.57
    isière
    -0.57
    POSITIVE LOGITS
    <bos>
    0.98
     (
    0.59
    AnchorTagHelper
    0.56
    onAttach
    0.56
    HostException
    0.54
    SpringRunner
    0.54
    BeginContext
    0.54
    WebControls
    0.53
    PointerException
    0.49
    yntaxException
    0.48
    Activations Density 2.685%

    No Known Activations